DeepSeek-R1 is the stronger all-rounder.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding, reasoning and long documents rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-R1 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+32.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+28.5points ahead
- Questions about very long textsLongBench v2+22.9points ahead
Where DeepSeek-V2.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- CodeforcesDeepSeek-R1 by 1993 rating points202935.6+1993 rating
- AIME 2024DeepSeek-R1 by 63.179.816.7+63.1
- Aider-PolyglotDeepSeek-R1 by 35.553.317.8+35.5
- MATHDeepSeek-R1 by 22.697.374.7+22.6
- MATH-500 (EM)DeepSeek-R1 by 22.697.374.7+22.6
- LiveCodeBenchDeepSeek-R1 by 21.763.541.8+21.7
- SimpleQADeepSeek-R1 by 19.930.110.2+19.9
- MMLU-ProDeepSeek-R1 by 17.88466.2+17.8
- FRAMES (Acc.)DeepSeek-R1 by 17.182.565.4+17.1
- MMLU-ReduxDeepSeek-R1 by 12.692.980.3+12.6
- MMLUDeepSeek-R1 by 10.490.880.4+10.4
- Chinese SimpleQA (C-SimpleQA)DeepSeek-R1 by 9.663.754.1+9.6
- AA IntelligenceDeepSeek-R1 by 4.811.46.6+4.8
- DROP (3-shot F1)DeepSeek-R1 by 4.492.287.8+4.4
- IFEvalDeepSeek-R1 by 2.783.380.6+2.7
- CLUEWSCDeepSeek-R1 by 2.492.890.4+2.4
Questions people ask
Which is better, DeepSeek-R1 or DeepSeek-V2.5?
DeepSeek-R1 wins all three areas where both have results: coding, reasoning and long documents. DeepSeek-V2.5 wins none.
Which is better for coding?
DeepSeek-R1. It wins the one coding test both models report.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.